Learning Multiple Conflicting Tasks with Artificial Evolution

Delphine Nicolay; Roli Andrea; Timoteo Carletti

doi:10.1007/978-3-319-12745-3_11

Learning Multiple Conflicting Tasks with Artificial Evolution

Delphine Nicolay, Roli Andrea, Timoteo Carletti

Résultats de recherche: Contribution dans un livre/un catalogue/un rapport/dans les actes d'une conférence › Chapitre (revu par des pairs) › Revue par des pairs

76 Téléchargements (Pure)

Résumé

The paper explores the issue of learning multiple competing tasks in the domain of artificial evolution. In particular, a robot is trained so as to be able to perform two different tasks at the same time, namely a gradient following and rough terrain avoidance behaviours. It is shown that, if the controller is trained to learn two tasks of different difficulty, then the robot performance is higher if the most difficult task is learnt first, before the combined learning of both tasks. An explanation to this superiority is also discussed, in comparison with previous results.

langue originale	Anglais
titre	Advances in Artificial Life and Evolutionary Computation
Sous-titre	9th Italian Workshop, WIVACE 2014, Vietri sul Mare, Italy, May 14-15, Revised Selected Papers
rédacteurs en chef	Clara Pizzuti, Giandomenico Spezzano
Editeur	Springer
Pages	127-139
Nombre de pages	13
Volume	445
ISBN (Electronique)	978-3-319-12745-3
ISBN (imprimé)	978-3-319-12744-6
Les DOIs	https://doi.org/10.1007/978-3-319-12745-3_11
Etat de la publication	Publié - 6 nov. 2014
Evénement	9th Italian Workshop on Artificial Life and Evolutionary Computation, WIVACE 2014 - Vietri sul Mare, Italie Durée: 14 mai 2014 → 15 mai 2014

Série de publications

Nom	Communications in Computer and Information Science
Volume	445
ISSN (imprimé)	18650929

Une conférence

Une conférence	9th Italian Workshop on Artificial Life and Evolutionary Computation, WIVACE 2014
Pays/Territoire	Italie
La ville	Vietri sul Mare
période	14/05/14 → 15/05/14

Accès au document

10.1007/978-3-319-12745-3_11

Wivace_correctionmanuscrit soumis, 362 KB

http://link.springer.com/chapter/10.1007/978-3-319-12745-3_11

consortium des équipements de calcul intensif
Champagne, B.
1/01/11 → 31/12/22
Projet: Recherche

Plateforme Technologique Calcul Intensif
Benoît Champagne (!!Manager)
Plateforme technologique Calcul intensif
Equipement/installations: Plateforme technolgique

Modélisation et apprentissage des réseaux de neurones artificiels
Auteur: NICOLAY, D., 22 juin 2012
Superviseur: Carletti, T. (Promoteur)
Student thesis: Master types › Master en sciences mathématiques

Fichier

Contient cette citation

Nicolay, D., Andrea, R., & Carletti, T. (2014). Learning Multiple Conflicting Tasks with Artificial Evolution. Dans C. Pizzuti, & G. Spezzano (eds.), Advances in Artificial Life and Evolutionary Computation: 9th Italian Workshop, WIVACE 2014, Vietri sul Mare, Italy, May 14-15, Revised Selected Papers (Vol 445, p. 127-139). (Communications in Computer and Information Science; Vol 445). Springer. https://doi.org/10.1007/978-3-319-12745-3_11

Nicolay, Delphine ; Andrea, Roli ; Carletti, Timoteo. / Learning Multiple Conflicting Tasks with Artificial Evolution. Advances in Artificial Life and Evolutionary Computation: 9th Italian Workshop, WIVACE 2014, Vietri sul Mare, Italy, May 14-15, Revised Selected Papers. Editeur / Clara Pizzuti ; Giandomenico Spezzano. Vol 445 Springer, 2014. p. 127-139 (Communications in Computer and Information Science).

@inbook{5fd703fb3313455482aa3a4bb38cdda4,

title = "Learning Multiple Conflicting Tasks with Artificial Evolution",

abstract = "The paper explores the issue of learning multiple competing tasks in the domain of artificial evolution. In particular, a robot is trained so as to be able to perform two different tasks at the same time, namely a gradient following and rough terrain avoidance behaviours. It is shown that, if the controller is trained to learn two tasks of different difficulty, then the robot performance is higher if the most difficult task is learnt first, before the combined learning of both tasks. An explanation to this superiority is also discussed, in comparison with previous results.",

keywords = "Artificial Intelligence, neural networks, evolutionary robotics, genetic algorithms",

author = "Delphine Nicolay and Roli Andrea and Timoteo Carletti",

year = "2014",

month = nov,

day = "6",

doi = "10.1007/978-3-319-12745-3_11",

language = "English",

isbn = "978-3-319-12744-6",

volume = "445",

series = "Communications in Computer and Information Science",

publisher = "Springer",

pages = "127--139",

editor = "Clara Pizzuti and Giandomenico Spezzano",

booktitle = "Advances in Artificial Life and Evolutionary Computation",

note = "9th Italian Workshop on Artificial Life and Evolutionary Computation, WIVACE 2014 ; Conference date: 14-05-2014 Through 15-05-2014",

}

Nicolay, D, Andrea, R & Carletti, T 2014, Learning Multiple Conflicting Tasks with Artificial Evolution. Dans C Pizzuti & G Spezzano (eds), Advances in Artificial Life and Evolutionary Computation: 9th Italian Workshop, WIVACE 2014, Vietri sul Mare, Italy, May 14-15, Revised Selected Papers. VOL. 445, Communications in Computer and Information Science, VOL. 445, Springer, p. 127-139, 9th Italian Workshop on Artificial Life and Evolutionary Computation, WIVACE 2014, Vietri sul Mare, Italie, 14/05/14. https://doi.org/10.1007/978-3-319-12745-3_11

Learning Multiple Conflicting Tasks with Artificial Evolution. / Nicolay, Delphine; Andrea, Roli; Carletti, Timoteo.
Advances in Artificial Life and Evolutionary Computation: 9th Italian Workshop, WIVACE 2014, Vietri sul Mare, Italy, May 14-15, Revised Selected Papers. Ed. / Clara Pizzuti; Giandomenico Spezzano. Vol 445 Springer, 2014. p. 127-139 (Communications in Computer and Information Science; Vol 445).

Résultats de recherche: Contribution dans un livre/un catalogue/un rapport/dans les actes d'une conférence › Chapitre (revu par des pairs) › Revue par des pairs

TY - CHAP

T1 - Learning Multiple Conflicting Tasks with Artificial Evolution

AU - Nicolay, Delphine

AU - Andrea, Roli

AU - Carletti, Timoteo

PY - 2014/11/6

Y1 - 2014/11/6

N2 - The paper explores the issue of learning multiple competing tasks in the domain of artificial evolution. In particular, a robot is trained so as to be able to perform two different tasks at the same time, namely a gradient following and rough terrain avoidance behaviours. It is shown that, if the controller is trained to learn two tasks of different difficulty, then the robot performance is higher if the most difficult task is learnt first, before the combined learning of both tasks. An explanation to this superiority is also discussed, in comparison with previous results.

AB - The paper explores the issue of learning multiple competing tasks in the domain of artificial evolution. In particular, a robot is trained so as to be able to perform two different tasks at the same time, namely a gradient following and rough terrain avoidance behaviours. It is shown that, if the controller is trained to learn two tasks of different difficulty, then the robot performance is higher if the most difficult task is learnt first, before the combined learning of both tasks. An explanation to this superiority is also discussed, in comparison with previous results.

KW - Artificial Intelligence

KW - neural networks

KW - evolutionary robotics

KW - genetic algorithms

U2 - 10.1007/978-3-319-12745-3_11

DO - 10.1007/978-3-319-12745-3_11

M3 - Chapter (peer-reviewed)

AN - SCOPUS:84916593100

SN - 978-3-319-12744-6

VL - 445

T3 - Communications in Computer and Information Science

SP - 127

EP - 139

BT - Advances in Artificial Life and Evolutionary Computation

A2 - Pizzuti, Clara

A2 - Spezzano, Giandomenico

PB - Springer

T2 - 9th Italian Workshop on Artificial Life and Evolutionary Computation, WIVACE 2014

Y2 - 14 May 2014 through 15 May 2014

ER -

Nicolay D, Andrea R, Carletti T. Learning Multiple Conflicting Tasks with Artificial Evolution. Dans Pizzuti C, Spezzano G, rédacteurs en chef, Advances in Artificial Life and Evolutionary Computation: 9th Italian Workshop, WIVACE 2014, Vietri sul Mare, Italy, May 14-15, Revised Selected Papers. Vol 445. Springer. 2014. p. 127-139. (Communications in Computer and Information Science). doi: 10.1007/978-3-319-12745-3_11

Learning Multiple Conflicting Tasks with Artificial Evolution

Résumé

Série de publications

Une conférence

Accès au document

Empreinte digitale

Projets

consortium des équipements de calcul intensif

Équipement

Plateforme Technologique Calcul Intensif

Thèses de l'étudiant

Modélisation et apprentissage des réseaux de neurones artificiels

Contient cette citation